Explore our innovative xLAM models and multi-agent framework. Witness how they revolutionize task execution for function calling in a live demo in a sales environment.
Important: This session is first come, first seated. You do not have a reserved seat.
Session Summary by Einstein: Salesforce AI research showcased a revolutionary vision for the future of enterprise productivity through Agentforce, introducing a multi-agent system empowered by large action models (LAMs). The session detailed the evolution from simple text-based AI responses to complex task execution by AI agents, emphasizing the in-house LAMs that will power the future of Agentforce. Demonstrating the capabilities of the Salesforce AI research team, they unveiled Xlam, a family of LAMs ranging from tiny to large, trained on over 1 million data points, and ranking number one in function-calling leaderboards. The team also introduced Agent Lite, an open-source framework for building multi-agent systems, and illustrated a real-world application with a fully autonomous customer service team that operates without human intervention.
Key Takeaways by Einstein:
• Salesforce has developed Xlam, a cutting-edge suite of large action models, designed to automate workflows and drive productivity across various devices and platforms.
• Agent Lite was announced as an open-source framework that facilitates the creation and orchestration of multi-agent systems, enhancing the potential for scalability and specialization.
• A live demonstration of a multi-agent system for customer service showcased the practical application of these models, offering a glimpse into the future of AI-driven enterprise solutions.
With sessions and hands-on activities led by product experts, visionaries, and fellow Trailblazers, Dreamforce offers a deep dive into the latest in CRM + AI + Data + Trust.
Merlinda Lu
Salesforce Developer, IBM
We use cookies on our website to improve website performance, to analyze website usage and to tailor content and offers to your interests.
By clicking “Accept All Cookies”, you consent to us placing these cookies. By clicking “Do Not Accept”, you reject the usage of such cookies. We always place cookies that do not require consent, which are necessary for the website to work properly.
For more information about the different cookies we are using, read the Privacy Statement. To change your cookie settings and preferences, click the Cookie Consent Manager button.
Cookie Consent Manager
Cookie Consent Manager
General Information
Required Cookies
Functional Cookies
Advertising Cookies
General Information
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.
